Limits...
An Example-Based Multi-Atlas Approach to Automatic Labeling of White Matter Tracts.

Yoo SW, Guevara P, Jeong Y, Yoo K, Shin JS, Mangin JF, Seong JK - PLoS ONE (2015)

Bottom Line: To further enhance the computational efficiency, we implemented our approach on the graphics processing unit (GPU).Through nested cross-validation we demonstrated that our approach yielded high classification performance.The average sensitivities for bundles in the left and right hemispheres were 89.5% and 91.0%, respectively, and their average false discovery rates were 14.9% and 14.2%, respectively.

View Article: PubMed Central - PubMed

Affiliation: Department of Biomedical Engineering, Korea University, Seoul, Republic of Korea; Department of Computer Science, KAIST, Daejeon, Republic of Korea.

ABSTRACT
We present an example-based multi-atlas approach for classifying white matter (WM) tracts into anatomic bundles. Our approach exploits expert-provided example data to automatically classify the WM tracts of a subject. Multiple atlases are constructed to model the example data from multiple subjects in order to reflect the individual variability of bundle shapes and trajectories over subjects. For each example subject, an atlas is maintained to allow the example data of a subject to be added or deleted flexibly. A voting scheme is proposed to facilitate the multi-atlas exploitation of example data. For conceptual simplicity, we adopt the same metrics in both example data construction and WM tract labeling. Due to the huge number of WM tracts in a subject, it is time-consuming to label each WM tract individually. Thus, the WM tracts are grouped according to their shape similarity, and WM tracts within each group are labeled simultaneously. To further enhance the computational efficiency, we implemented our approach on the graphics processing unit (GPU). Through nested cross-validation we demonstrated that our approach yielded high classification performance. The average sensitivities for bundles in the left and right hemispheres were 89.5% and 91.0%, respectively, and their average false discovery rates were 14.9% and 14.2%, respectively.

No MeSH data available.


Comparison with a Guevara et al.’s method [33].The left column represents expert-labeled bundles, the middle column depicts bundles obtained using our approach, and the right column shows bundles acquired using the Guevara et al.’s method. Our approach obtained more accurate labeling results than Guevara et al.’s method [33].
© Copyright Policy
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC4520495&req=5

pone.0133337.g010: Comparison with a Guevara et al.’s method [33].The left column represents expert-labeled bundles, the middle column depicts bundles obtained using our approach, and the right column shows bundles acquired using the Guevara et al.’s method. Our approach obtained more accurate labeling results than Guevara et al.’s method [33].

Mentions: In Fig 10, the left column presents the expert-labeled bundles of an example subject, the middle column exhibits bundles obtained using our approach, and the right column shows bundles acquired using the method of Guevara et al. [33]. By comparing the bundle shapes in the left and right columns, we can verify that the labeling results by our approach are more similar to the expert-provided results than the labeling results from the Guevara et al.’s method. For CG and SLF, the labeling results of the latter method contain a few outlier tracts. These outliers may result from accidental matching of outliers with example data. Our method can reduce this type of labeling error by using the voting scheme.


An Example-Based Multi-Atlas Approach to Automatic Labeling of White Matter Tracts.

Yoo SW, Guevara P, Jeong Y, Yoo K, Shin JS, Mangin JF, Seong JK - PLoS ONE (2015)

Comparison with a Guevara et al.’s method [33].The left column represents expert-labeled bundles, the middle column depicts bundles obtained using our approach, and the right column shows bundles acquired using the Guevara et al.’s method. Our approach obtained more accurate labeling results than Guevara et al.’s method [33].
© Copyright Policy
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC4520495&req=5

pone.0133337.g010: Comparison with a Guevara et al.’s method [33].The left column represents expert-labeled bundles, the middle column depicts bundles obtained using our approach, and the right column shows bundles acquired using the Guevara et al.’s method. Our approach obtained more accurate labeling results than Guevara et al.’s method [33].
Mentions: In Fig 10, the left column presents the expert-labeled bundles of an example subject, the middle column exhibits bundles obtained using our approach, and the right column shows bundles acquired using the method of Guevara et al. [33]. By comparing the bundle shapes in the left and right columns, we can verify that the labeling results by our approach are more similar to the expert-provided results than the labeling results from the Guevara et al.’s method. For CG and SLF, the labeling results of the latter method contain a few outlier tracts. These outliers may result from accidental matching of outliers with example data. Our method can reduce this type of labeling error by using the voting scheme.

Bottom Line: To further enhance the computational efficiency, we implemented our approach on the graphics processing unit (GPU).Through nested cross-validation we demonstrated that our approach yielded high classification performance.The average sensitivities for bundles in the left and right hemispheres were 89.5% and 91.0%, respectively, and their average false discovery rates were 14.9% and 14.2%, respectively.

View Article: PubMed Central - PubMed

Affiliation: Department of Biomedical Engineering, Korea University, Seoul, Republic of Korea; Department of Computer Science, KAIST, Daejeon, Republic of Korea.

ABSTRACT
We present an example-based multi-atlas approach for classifying white matter (WM) tracts into anatomic bundles. Our approach exploits expert-provided example data to automatically classify the WM tracts of a subject. Multiple atlases are constructed to model the example data from multiple subjects in order to reflect the individual variability of bundle shapes and trajectories over subjects. For each example subject, an atlas is maintained to allow the example data of a subject to be added or deleted flexibly. A voting scheme is proposed to facilitate the multi-atlas exploitation of example data. For conceptual simplicity, we adopt the same metrics in both example data construction and WM tract labeling. Due to the huge number of WM tracts in a subject, it is time-consuming to label each WM tract individually. Thus, the WM tracts are grouped according to their shape similarity, and WM tracts within each group are labeled simultaneously. To further enhance the computational efficiency, we implemented our approach on the graphics processing unit (GPU). Through nested cross-validation we demonstrated that our approach yielded high classification performance. The average sensitivities for bundles in the left and right hemispheres were 89.5% and 91.0%, respectively, and their average false discovery rates were 14.9% and 14.2%, respectively.

No MeSH data available.